[Gimle-users] Bore/Gimle up
kent at nsc.liu.se
kent at nsc.liu.se
Fri Dec 11 14:00:36 CET 2009
kent at nsc.liu.se writes:
> This morning we have experienced a failure in computer room Hangaren,
> that has resulted in total power loss.
>
> Bore and Gimle are down at the moment.
Bore is up again since quite some time (told Lars M and Magnus L on the
phone). Node n25 still down pending service.
Gimle is up again with the following two exceptions:
- Some nodes on the nehalem partition are down pending service.
- The rossby14 filesystem has been unmounted to speed up RAID rebuild on
one of the object servers, where a disk failed just before the power
was cut and another disk is rebuilding. We will not take any chances
with that one. With the filesystem dormant, the rebuild will be
quicker.
> We are investigating and will report back when we have more information.
A faulty PLC (control computer) in the cooling system has been replaced.
We will have to get back to you later with more info on the cause.
--
Kent Engström, National Supercomputer Centre
kent at nsc.liu.se, +46 13 28 4444
More information about the Gimle-users
mailing list